Share Email Print
cover

Proceedings Paper • new

Image processing and machine learning techniques to automate diagnosis of Lugol's iodine cervigrams for a low-cost point-of-care digital colposcope
Author(s): Mercy Nyamewaa Asiedu; Anish Simhal; Christopher T. Lam; Jenna Mueller; Usamah Chaudhary; John W. Schmitt; Guillermo Sapiro; Nimmi Ramanujam
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

The world health organization recommends visual inspection with acetic acid (VIA) and/or Lugol’s Iodine (VILI) for cervical cancer screening in low-resource settings. Human interpretation of diagnostic indicators for visual inspection is qualitative, subjective, and has high inter-observer discordance, which could lead both to adverse outcomes for the patient and unnecessary follow-ups. In this work, we a simple method for automatic feature extraction and classification for Lugol’s Iodine cervigrams acquired with a low-cost, miniature, digital colposcope. Algorithms to preprocess expert physician-labelled cervigrams and to extract simple but powerful color-based features are introduced. The features are used to train a support vector machine model to classify cervigrams based on expert physician labels. The selected framework achieved a sensitivity, specificity, and accuracy of 89.2%, 66.7% and 80.6% with majority diagnosis of the expert physicians in discriminating cervical intraepithelial neoplasia (CIN +) relative to normal tissues. The proposed classifier also achieved an area under the curve of 84 when trained with majority diagnosis of the expert physicians. The results suggest that utilizing simple color-based features may enable unbiased automation of VILI cervigrams, opening the door to a full system of low-cost data acquisition complemented with automatic interpretation.

Paper Details

Date Published: 13 February 2018
PDF: 10 pages
Proc. SPIE 10485, Optics and Biophotonics in Low-Resource Settings IV, 1048508 (13 February 2018); doi: 10.1117/12.2282792
Show Author Affiliations
Mercy Nyamewaa Asiedu, Ctr. for Global Women's Health Technologies, Duke Univ. (United States)
Duke Global Health Institite, Duke Univ. (United States)
Anish Simhal, Duke Univ. (United States)
Christopher T. Lam, Ctr. for Global Women's Health Technologies, Duke Univ. (United States)
Duke Global Health Institite, Duke Univ. (United States)
Jenna Mueller, Ctr. for Global Women's Health Technologies, Duke Univ. (United States)
Duke Global Health Institite, Duke Univ. (United States)
Usamah Chaudhary, Duke Univ. (United States)
John W. Schmitt, Duke Univ. (United States)
Guillermo Sapiro, Duke Univ. (United States)
Nimmi Ramanujam, Ctr. for Global Women's Health Technologies, Duke Univ. (United States)
Duke Global Health Institite, Duke Univ. (United States)


Published in SPIE Proceedings Vol. 10485:
Optics and Biophotonics in Low-Resource Settings IV
David Levitz; Aydogan Ozcan; David Erickson, Editor(s)

© SPIE. Terms of Use
Back to Top